# EMMA framework uses generative visual models to improve visual generalization of VLA manipulation policies

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/ps01lcgi3yti71hwjajsm6i4q
- Original: https://arxiv.org/abs/2509.22407

## Summary

The EMMA framework enhances vision-language-action (VLA) policies through a generative data engine and training pipeline, addressing the high cost of collecting robot manipulation data across varied appearances. Its core component, DreamTransfer, is based on a diffusion Transformer and generates multi-view-consistent, geometrically plausible manipulation videos, supporting text-driven editing of foreground, background, and lighting while preserving 3D structure.